Uncertainty Aware Functional Behavior Prediction and Material Fatigue Assessment for Circular Factory

循环工厂中具备不确定性感知的功能行为预测与材料疲劳评估

Abstract: Returned products in circular factories re-enter production with heterogeneous degradation states, usage histories, and remaining capability. Reuse cannot be decided from the current inspection alone, because future function fulfillment and component integrity may evolve differently under the next service scenario. Existing PHM approaches support degradation prediction, but often target fixed operating conditions or isolated component benchmarks, while material-fatigue assessment is rarely linked to system-level functional prognosis.

摘要： 在循环工厂中，退回的产品以异构的退化状态、使用历史和剩余能力重新进入生产流程。仅凭当前的检查无法决定其是否可以再利用，因为在下一个服务场景下，未来的功能实现和组件完整性可能会发生不同的演变。现有的故障预测与健康管理（PHM）方法支持退化预测，但通常针对固定的运行条件或孤立的组件基准，而材料疲劳评估很少与系统级的功能预测相关联。

This paper addresses this gap for an angle grinder by combining uncertainty-aware functional prediction with component-level fatigue assessment in an instance-specific reliability workflow. The proposed framework combines the current tool state with recent force—torque usage windows. A convolutional encoder extracts loading patterns from spindle forces and shaft torque, and an LSTM backbone predicts nine functional variables as Gaussian mean and variance estimates.

本文针对角磨机解决了这一空白，通过在特定实例的可靠性工作流中，将具备不确定性感知的功能预测与组件级疲劳评估相结合。所提出的框架将当前的工具状态与近期的力-扭矩使用窗口相结合。卷积编码器从主轴力和轴扭矩中提取负载模式，LSTM 主干网络则预测九个功能变量，并给出高斯均值和方差估计。

In parallel, the same loading history is translated into output-shaft fatigue information through finite-element-supported stress reconstruction, S—N/Miner damage evaluation with Haibach extension, and Paris-law crack-growth analysis. A streaming replay algorithm consolidates both branches into functional, material, and system reliability trajectories.

与此同时，通过有限元支持的应力重构、带有 Haibach 扩展的 S-N/Miner 损伤评估以及 Paris 定律裂纹扩展分析，将相同的负载历史转化为输出轴的疲劳信息。流式重放算法将这两个分支整合为功能、材料和系统可靠性轨迹。

Held-out tests show mean 2%-tolerance accuracy of 0.9652 across nine outputs. Thermal variables are predicted near-perfectly, while drive motor current and load speed remain the most demanding dynamic outputs, with R² values of 0.9750 and 0.9924. Torque history is especially important for these variables, and the conventional LSTM outperforms GRU and xLSTM in the short-history setting. Reliability calibration is most informative for drive motor current, where predicted and observed exceedance probabilities…

留出法测试显示，在九个输出变量中，2% 容差范围内的平均准确率为 0.9652。热变量的预测几乎完美，而驱动电机电流和负载速度仍然是最具挑战性的动态输出，其 R² 值分别为 0.9750 和 0.9924。扭矩历史对于这些变量尤为重要，且在短历史记录设置下，传统的 LSTM 表现优于 GRU 和 xLSTM。可靠性校准对于驱动电机电流的信息量最大，其中预测的和观察到的超限概率……